Remove the stored Hiro API key from ~/.aibtc/config.json. If HIRO_API_KEY is set in the environment, that will still be used as a fallback.
AI agents call delete_hiro_api_key to permanently remove resources in Aibtc — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes stored credentials from a configuration file. While the fallback to HIRO_API_KEY environment variable limits some impact, the primary action is irreversible deletion of user-managed authentication material. This is more severe than Write (reversible modification) and qualifies as Destructive.
From the tool's definition Tool name is 'delete_hiro_api_key' and description states 'Remove the stored Hiro API key from ~/.aibtc/config.json'. The verb 'Remove' combined with deletion of persistent configuration data indicates irreversible data destruction.
Documented attack patterns abuse exactly the kind of access delete_hiro_api_key gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Aibtc, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_hiro_api_key:
{
"version": "1",
"default": "deny",
"hide": [
"delete_hiro_api_key"
]
} delete_hiro_api_key disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Remove the stored Hiro API key from ~/.aibtc/config.json. If HIRO_API_KEY is set in the environment, that will still be used as a fallback. It is categorised as a Destructive tool in the Aibtc MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Aibtc MCP server in PolicyLayer and add a rule for delete_hiro_api_key: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Aibtc. Nothing to install.
delete_hiro_api_key is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_hiro_api_key rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for delete_hiro_api_key. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
delete_hiro_api_key is provided by the Aibtc MCP server (aibtcdev/aibtc-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Aibtc, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
353 Aibtc tools catalogued and risk-classified — across an index of 43,000+ MCP servers.